Who we'd reach at Solvd, Inc.Found and reached by Power Apply
Best leadHiring manager
Leads the team this role joins
Recruiter
In-house, owns the opening
Posted this job
Put the opening up
From your own Gmail and LinkedIn.
About the role
Solvd is hiring a remote, full-time senior data engineer in the United States to own the retrieval work for a client's Agent Assist platform. The role builds a secure, versioned RAG retrieval API, the Amazon Bedrock and OpenSearch infrastructure beneath it, and quality monitoring, then supports a pilot and handover.
What you’ll do
- Provision the Bedrock Knowledge Base and OpenSearch Serverless collection from infrastructure code, with specified embedding, chunking, and metadata.
- Implement hybrid vector and keyword retrieval with metadata filtering, then tune top-k, thresholds, and reranking against a test suite.
- Build the retrieval API on API Gateway and Lambda, with versioning, auth, per-client rate limits, usage metrics, error responses, and citation payloads.
- Enforce permissions at query time so restricted content never reaches unentitled callers.
- Provide a Bedrock retrieve-and-generate reference endpoint for pilot validation.
- Build a quality dashboard covering relevance, grounding, citations, permission tests, freshness, latency, errors, and capacity.
- Support the contact center pilot by capturing retrieval misses and re-running the suite before changes ship.
- Write runbooks for model changes, re-embedding, and index rebuilds, including their cost impact.
- Hand over to client platform owners using a readiness checklist.
What they’re looking for
- 4+ years as a software or ML engineer, including at least one RAG or enterprise search system in production, measured with an evaluation suite.
- Hands-on work with Amazon Bedrock Knowledge Bases, retrieval APIs, and OpenSearch Serverless vector search with hybrid queries and filters.
- Python, with Lambda APIs behind API Gateway that include auth, versioning, and throttling.
- Infrastructure as code with Terraform or AWS CDK, and CI for deployment into client-owned accounts.
- Practical understanding of chunking, embeddings, reranking, and the trade-offs between relevance, latency, and cost.
- Experience building operational dashboards in CloudWatch or a similar tool.
Nice to have
- AWS Certified Generative AI Developer Professional or AWS Certified Machine Learning Engineer Associate.
- Experience with RAG evaluation metrics such as faithfulness, context precision and recall, and citation accuracy.
- Experience integrating with a contact center Agent Assist product as an API provider.
- Familiarity with Bedrock Guardrails and permission-aware retrieval over Microsoft 365 content.
Skills
Amazon BedrockAmazon OpenSearch ServerlessRetrieval-Augmented GenerationVector SearchHybrid SearchPythonAWS LambdaAmazon API GatewayTerraformAWS CDKCloudWatchEmbeddingsRerankingChunkingBedrock GuardrailsInfrastructure as CodeCI/CDData Engineering
Questions about this role
Is this role remote?
Yes, it is listed as remote in the United States.
How many years of experience are needed?
4 or more years as a software or ML engineer.
Which AWS services are involved?
Amazon Bedrock, OpenSearch Serverless, Lambda, API Gateway, CloudWatch, and infrastructure as code with Terraform or CDK.